TensorFlow 1.9 Docs

TensorFlow 1.9 Documentation TensorFlow is an open source software library for numerical computation using data flow graphs. The graph nodes represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) that flow between them. This flexible architecture lets you deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device without rewriting code. TensorFlow also includes TensorBoard, a data visualization toolkit. TensorFlow was originally developed by researchers and engineers working on the Google Brain team within Google's Machine Intelligence Research organization for the purposes of conducting machine learning and deep neural networks research. The system is general enough to be applicable in a wide variety of other domains, as well. Attribution: the TensorFlow logo and any related marks are trademarks of Google Inc. Table of Content Install TensorFlow Install TensorFlow on Ubuntu Install TensorFlow on macOS Install TensorFlow on Windows Install TensorFlow on Raspbian Install TensorFlow from Sources Transitioning to TensorFlow 1.0 Install TensorFlow for Java Install TensorFlow for Go Install TensorFlow for C TensorFlow Guide Keras Eager Execution Importing Data Introduction to Estimators Premade Estimators Checkpoints Feature Columns Datasets for Estimators Creating Custom Estimators Using GPUs Using TPUs Introduction Tensors Variables Graphs and Sessions Save and Restore Embeddings TensorFlow Debugger Visualizing Learning Graphs Histograms TensorFlow Version Compatibility Frequently Asked Questions Overview Basic classification Text classification Regression Overfitting and underfitting Save and restore models Overview Custom training: walkthrough Linear model with Estimators Text classifier with TF-Hub Build a CNN using Estimators Image recognition Image retraining Advanced CNN Recurrent neural network Drawing classification Simple audio recognition Vector representations of words Kernel methods Large-scale linear models Mandelbrot set Partial differential equations Next steps Deploy Distributed TensorFlow How to run TensorFlow on Hadoop How to run TensorFlow on S3 Deploy to JavaScript Introduction Architecture Overview Installation Serving a TensorFlow Model RESTful API Building Standard TensorFlow ModelServer Serving Inception Model with TensorFlow Serving and Kubernetes Creating a new kind of servable Creating a module that discovers new servable paths SignatureDefs in SavedModel for TensorFlow Serving Using TensorFlow Serving via Docker Performance Performance Guide Input Pipeline Performance Guide Benchmarks Fixed Point Quantization XLA Overview Broadcasting semantics Developing a new backend for XLA Using JIT Compilation Operation Semantics Shapes and Layout Using AOT compilation Extend TensorFlow Architecture Adding a New Op Adding a Custom Filesystem Plugin Reading custom file and record formats TensorFlow in other languages A Tool Developer's Guide to TensorFlow Model Files Overview Introduction to TensorFlow Lite Developer Guide Android Demo App iOS Demo App Performance Introduction to TensorFlow Mobile Building TensorFlow on Android Building TensorFlow on iOS Integrating TensorFlow libraries Preparing models for mobile deployment Optimizing for mobile Community Roadmap Contributing to TensorFlow Mailing Lists User Groups Writing TensorFlow Documentation TensorFlow Style Guide Defining and Running Benchmarks About TensorFlow TensorFlow In Use TensorFlow White Papers Attribution Overview Installation Using a Module Creating a New Module Fine-Tuning Hosting a Module Image Retraining Text Classification Overview Common Signatures for Images Common Signatures for Text Overview add_signature create_module_spec get_expected_image_size get_num_image_channels image_embedding_column LatestModuleExporter load_module_spec Module ModuleSpec register_module_for_export text_embedding_column Overview Image Modules Text Modules Other Modules